Tasks

The tasks for this project are outlined in the vui_notebook.ipynb in three steps. Follow all the instructions, which include implementing code in sample_models.py, answering questions, and providing results. The following list is a summary of the required tasks.

Step 1 - Feature Extraction

• Execute all code cells to extract features from raw audio

Step 2 - Acoustic Model

• Implement the code for Models 1, 2, 3, and 4 in sample_models.py
• Train Models 0, 1, 2, 3, 4 in the notebook
• Execute the comparison code in the notebook
• Answer Question 1 in the notebook regarding the comparison
• Implement the code for the Final Model in sample_models.py
• Train the Final Model in the notebook
• Answer Question 2 in the notebook regarding your final model

Step 3 - Decoder

• Execute the prediction code in the notebook